On the capacity of a quantum perceptron for storing biased patterns

DOI10.1088/1751-8121/AD125BOpenAlexW4389328845MaRDI QIDQ6138886FDOQ6138886

Authors F. Benatti, Giovanni Gramegna, Stefano Mancini

Publication date 16 January 2024

Published in Journal of Physics A: Mathematical and Theoretical (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2304.14393

zbMATH Keywords

storage capacityquantum neural networksquantum perceptron

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX) Quantum theory (81-XX)

Abstract: Although different architectures of quantum perceptrons have been recently put forward, the capabilities of such quantum devices versus their classical counterparts remain debated. Here, we consider random patterns and targets independently distributed with biased probabilities and investigate the storage capacity of a continuous quantum perceptron model that admits a classical limit, thus facilitating the comparison of performances. Such a more general context extends a previous study of the quantum storage capacity where using statistical mechanics techniques in the limit of a large number of inputs, it was proved that no quantum advantages are to be expected concerning the storage properties. This outcome is due to the fuzziness inevitably introduced by the intrinsic stochasticity of quantum devices. We strengthen such an indication by showing that the possibility of indefinitely enhancing the storage capacity for highly correlated patterns, as it occurs in a classical setting, is instead prevented at the quantum level.

Recommendations

• Pattern capacity of a single quantum perceptron
• A QUANTUM PERCEPTRON
• Simulating a perceptron on a quantum computer
• Storage of correlated patterns in a perceptron
• Information capacity of a perceptron

Cites work

• scientific article; zbMATH DE number 1273988 (Why is no real title available?)
• Continuous variable quantum perceptron
• Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition
• Mean field models for spin glasses. Volume I: Basic examples.
• Pattern capacity of a single quantum perceptron
• Quantum machine learning. What quantum computing means to data mining
• Rigorous solution of the Gardner problem
• Spin-glass theory for pedestrians
• Statistical mechanics of learning
• The quest for a quantum neural network
• The space of interactions in neural network models
• Threshold-induced phase transitions in perceptrons

This page was built for publication: On the capacity of a quantum perceptron for storing biased patterns

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138886)